检索结果-内蒙古大学图书馆

A weakly supervised pavement crack segmentation based on adversarial learning and transformers

Multimedia Systems 2025年第3期31卷 1-21页

作者： Apedo, Yvon Tao, Huanjie School of Computer Science Northwestern Polytechnical University Xi’an People’s Republic of China Engineering and Research Center of Embedded Systems Integration (Northwestern Polytechnical University) Ministry of Education Xi’an People’s Republic of China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an People’s Republic of China

While pixel-level crack segmentation has demonstrated significant potential in infrastructure inspections, its reliance on detailed annotations poses challenges for widespread adoption due to the time-consuming and expensive nature of such labeling. In response, weakly supervised crack segmentation has garnered attention as it eliminates the need for pixel-level annotations. However, existing methods, primarily based on class activation maps (CAM), involve complex training processes and suffer from poor performance due to misalignment between CAM-generated labels and the true target in the image. To address these challenges, we propose a weakly supervised approach for crack segmentation that simultaneously generates synthetic crack images and performs segmentation through adversarial learning. Unlike traditional methods that rely on coarse labels, our approach leverages synthetic crack images with corresponding labels, effectively eliminating issues of misalignment and noisy pseudo-labels. Our method introduces an encoder-decoder architecture for the segmentation model, incorporating a Transformer-based Feature Enhancement module (TFE) in the encoder. This module is specifically designed to capture long-range dependencies and efficiently integrate both high- and low-level features. Additionally, the model includes a Hilo block to extract both high- and low-frequency information from the images, along with a Progressive Shrinking Decoder (PSD) to aggregate and refine adjacent feature maps. Extensive experiments were conducted, and our model achieved an ODS of 67.12% on the CrackForest dataset, 60.11% on the Crack500 dataset, and 44.80% on the AEL dataset. These results demonstrate that our model outperforms several existing weakly supervised pavement segmentation methods across these datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LLM Knows Geometry Better than Algebra: Numerical Understanding of LLM-Based Agents in A Trading Arena

arXiv

引用

arXiv 2025年

作者： Ma, Tianmi Du, Jiawei Huang, Wenxin Wang, Wenjie Xie, Liang Zhong, Xian Zhou, Joey Tianyi Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University China Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore School of Computing National University of Singapore Singapore School of Science Wuhan University of Technology China

Recent advancements in large language models (LLMs) have significantly improved performance in natural language processing tasks. However, their ability to generalize to dynamic, unseen tasks, particularly in numerical reasoning, remains a challenge. Existing benchmarks mainly evaluate LLMs on problems with predefined optimal solutions, which may not align with real-world scenarios where clear answers are absent. To bridge this gap, we design the Agent Trading Arena, a virtual numerical game simulating complex economic systems through zero-sum games, where agents invest in stock portfolios. Our experiments reveal that LLMs, including GPT-4o, struggle with algebraic reasoning when dealing with plain-text stock data, often focusing on local details rather than global trends. In contrast, LLMs perform significantly better with geometric reasoning when presented with visual data, such as scatter plots or K-line charts, suggesting that visual representations enhance numerical reasoning. This capability is further improved by incorporating the reflection module, which aids in the analysis and interpretation of complex data. We validate our findings on NASDAQ STOCK dataset, where LLMs demonstrate stronger reasoning with visual data compared to text. Our code and data are publicly available at https://***/wekjsdvnm/***. © 2025, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

An Anchor-Free Refining Feature Pyramid Network for Dense and Multioriented Wheat Spikes Detection under UAV

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Jiao, Lin Liu, Haiyun Liang, Zheng Chen, Peng Wang, Rujing Liu, Kang Anhui University National Engineering Research Center for Agro-Ecological Big Data Analysis and Application School of Internet Hefei230601 China Hefei Institutes of Physical Science Chinese Academy of Sciences Institute of Intelligent Machines Hefei230031 China University of Science and Technology of China Science Island Branch Graduate School Anhui Hefei230031 China Anhui University School of Internet Hefei230031 China School of Internet Institutes of Physical Science and Information Technology Anhui University National Engineering Research Center for Agro-Ecological Big Data Analysis and Application Anhui Hefei230601 China Institute of Intelligent Machines Hefei Institutes of Physical Science Chinese Academy of Science Hefei230031 China Hong Kong Polytechnic University Department of Aeronautical and Aviation Engineering Hong Kong

The number of wheat spikes is a crucial index for evaluating the yield, and the precise detection of wheat spikes in an image plays an important role. Among various methods, deep learning-based approaches show impressive results in the task of wheat spike detection. However, the precise detection and recognition of wheat spike encounters large challenges due to complicated backgrounds, arbitrary orientations, and dense distribution in wheat spike images. To alleviate these issues, we have developed an anchor-free refining feature pyramid network (AFRFPN) that gets rid of horizontal bounding boxes (HBBs) from the network. First, the refining feature pyramid network (RFPN) has been introduced into extract richer features of wheat spike with highly variant appearances and multiple scales. Then, learning from the idea of coarse-to-fine, the two-stage anchor-free oriented detection (AFOD) module has been designed. The AFOD module first generates a set of coarse detection (CoDet) results in the way of anchor-free and then further fines them to achieve high-quality predicting bounding boxes (BBs). The number of wheat spike images is insufficient, resulting in poor performance of wheat spike detection modules. To mitigate the lack of the data in the task of oriented wheat spike detection, based on the global wheat head detection (GWHD) dataset, we released a new large-scale wheat spike dataset by relabeling the samples, termed it as rotated GWHD (R-GWHD) dataset. Massive experiments show that the proposed method can achieve 90.6% mAP and 96.7% recall, outperforming other state-of-the-art methods. Additionally, the experiments related to the counting of wheat spikes have been conducted, showing that the developed module can achieve the MAE of 4.95 and RMSE of 7.68, which demonstrates the excellent performance of the proposed method. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

PseudoSC: A Binary Approximation to Stochastic Computing within Latent Operation-Space for Ultra-Lightweight on-Edge DNNs 23

PseudoSC: A Binary Approximation to Stochastic Computing wit...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Jihe Wang Zhaoqing Wang Danghui Wang School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350323481

Recently, stochastic computing (SC) is increasingly popular in constructing MAC for on-edge DNNs benefiting from its outstanding energy-efficiency, including its adequate precision and gatelevel operation. However, current SC-DNN systems always include a lot of costly SNGs/APCs for inevitably switches between binary and stochastic domains, which mortgages incongruous resources to pay the "bill" of the domain-switches and impedes highly-concurrent deployments. In this work, PseudoSC, a binary approximation to low-discrepancy SC, is proposed to totally remove the domain-switch for SNG/APC-free SC-DNNs. Its basic idea is to virtually re-arrange a couple of stochastic operands into a 2-D latent op-space, in which, original Monte Carlo sampling can be partitioned into three sub-ops, i.e., two fixed binary-ops and a fractal recursion. In theory, the recursion forms an isomorphic partition of the sampling repeated in smaller scales until the binary base-case achieved, as a result, a SC-op is well approximated only with binary-ops. Based on above theory, a multi-lane micro-architecture is designed to unroll the recursion within a few cycles and its advantages on hardware saving is verified under popular DNNs. The evaluation shows that the DNN-models with our schemes achieve 98.7% accuracy of the fixed-point implementations, which significantly outperform other SOTA methods. In addition, its reduced structure improves the power efficiency by 3.67 times on average.

关键词： stochastic computing

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Feature Selection With Multi-Scale Fuzzy Information Fusion: From Both Global and Local Perspectives

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Zhou, Nan Liao, Shujiao Chen, Hongmei Ding, Weiping Lu, Yaqian Minnan Normal University School of Mathematics and Statistics Fujian Key Laboratory of Granular Computing and Applications Zhangzhou363000 China Southwest Jiaotong University School of Computing and Artificial Intelligence National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

In reality, the laborious nature of label annotation leads to the widespread existence of limited labeled data. Moreover, multi-scale data have received widespread attention due to its rich knowledge representation. However, current research on multi-scale data primarily focuses on supervised learning environments, while semi-supervised feature selection for multi-scale data with limited labels remains inadequately explored. Meanwhile, existing studies on multi-scale data often emphasize selecting optimal scales and further conducting feature selection, but this strategy may result in losing potentially valuable information from other scales. To overcome these limitations, by adopting a multi-scale fuzzy information fusion mechanism, this article proposes two new semi-supervised feature selection approaches for multi-scale data with limited labels from both global and local perspectives. Initially, by fusing fuzzy information at various scales, a label learning method is proposed to convert the decision of missing labels into a fuzzy decision of label distribution. Subsequently, label-distributed multi-scale fuzzy global and local rough sets are constructed from global and local perspectives, respectively. Based on the two models, two semi-supervised feature selection algorithms are developed based on global and local multi-scale fuzzy information fusion. Experimental results demonstrate that, compared to other advanced feature selection algorithms, the two proposed algorithms can effectively handle multi-scale data with limited labels and exhibit superior classification performance, computational efficiency and robustness. © 1993-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Robust Indoor Person Re-Identification with Multimodal Training

引用

IEEE Internet of Things Journal 2025年

作者： Su, Can Xue, Xinlei Ma, Lei Zhang, Xiaolong Yan, Wei Bian, Kaigui Peking University School of Computer Science AI Innovation Center National Engineering Laboratory for Big Data Analysis and Applications Beijing100871 China Peking University School of Computer Science Beijing100871 China Peking University Beijing Academy of Artificial Intelligence National Biomedical Imaging Center College of Future Technology National Key Laboratory for Multimedia Information Processing Beijing100871 China Beihang University Beijing100191 China

Existing person re-identification (ReID) methods mainly rely on images and videos to match persons across cameras, yet visual data captured by cameras are vulnerable to environmental interferences (e.g. illumination and occlusion) or personal appearance changes, leading to performance degradation under such scenes. Meanwhile, the popularization of Wi-Fi networks has allowed probe requests to be captured for mobile sensing applications such as crowd counting and trajectory estimation. However, the MAC address randomization technique adopted by modern devices breaks the association of probe requests and adversely affects the functionality of these applications. In this paper, we propose MaRPA, the first multimodal training approach that incorporates both videos and Wi-Fi probe requests to simultaneously promote tasks of probe requests association and person ReID. MaRPA first distinguishes among pairwise probe request frames through a contrastive learning model. It then matches video and probe request sequences by exploring their similarities from the position and the vision aspects. Matched videos and probe requests provide complementary information and generate more robust features for both tasks. To evaluate MaRPA, we contribute a new dataset containing synchronous videos and probe requests data for probe requests association and person ReID. Experimental results demonstrate the effectiveness of our approach. For probe requests association, it achieves > 85% discrimination accuracy and > 0.90 V-measure score;for person ReID, it achieves 75.8% mAP and 90.6% Rank-1, improving state-of-the-art video-based ReID methods by over 40% © 2014 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image analysis

arXiv

引用

arXiv 2025年

作者： Che, Haoxuan Wu, Yifei Jin, Haibo Xia, Yong Chen, Hao Department of Computer Science and Engineering Hong Kong University of Science and Technology University Hong Kong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Department of Computer Science and Engineering Department of Chemical and Biological Engineering Division of Life Science Hong Kong University of Science and Technology Hong Kong

Federated domain generalization aims to train a global model from multiple source domains and ensure its generalization ability to unseen target domains. Due to the target domain being with unknown domain shifts, attempting to approximate these gaps by source domains may be the key to improving model generalization capability. Existing works mainly focus on sharing and recombining local domain-specific attributes to increase data diversity and simulate potential domain shifts. However, these methods may be insufficient since only the local attribute recombination can be hard to touch the out-of-distribution of global data. In this paper, we propose a simple-yet-efficient framework named Federated Domain Adversarial Generation (FedDAG). It aims to simulate the domain shift and improve the model generalization by adversarially generating novel domains different from local and global source domains. Specifically, it generates novel-style images by maximizing the instance-level feature discrepancy between original and generated images and trains a generalizable task model by minimizing their feature discrepancy. Further, we observed that FedDAG could cause different performance improvements for local models. It may be due to inherent data isolation and heterogeneity among clients, exacerbating the imbalance in their generalization contributions to the global model. Ignoring this imbalance can lead the global model’s generalization ability to be sub-optimal, further limiting the novel domain generation procedure. Thus, to mitigate this imbalance, FedDAG hierarchically aggregates local models at the within-client and across-client levels by using the sharpness concept to evaluate client model generalization contributions. Extensive experiments across four medical benchmarks demonstrate FedDAG’s ability to enhance generalization in federated medical scenarios. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Personalized Hierarchical Federated Learning towards Heterogeneous Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年

作者： Zhang, Puning Shao, Shuman Wu, Chao Yang, Zhigang Zhang, Ruoying Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China Chongqing400065 China Chongqing Innovation Center of Industrial Big-Data Co. Ltd National Engineering Laboratory for Industrial Big-data Application Technology Chongqing400707 China China Merchants Testing Vehicle Technology Research Institute Co. Ltd Chongqing404100 China Chongqing University of Posts and Telecommunications School of Cyber Security and Information Law Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China China China Academy of Information and Communications Beijing100083 China

High mobility and non-independent and identically distributed (non-iid) data in the Internet of Vehicles (IoV) pose challenges for the convergence speed and accuracy of federated learning model training. Traditional federated learning approaches fail to account for the unique characteristics of local vehicle data, limiting the model performances. To address this, we propose a personalized hierarchical federated learning method tailored for heterogeneous IoV. Our approach customizes models for each vehicle, enhancing their performance on local data. We introduce a network-aware client selection method that dynamically chooses vehicle clients based on their spatiotemporal distribution and changing channel conditions. Additionally, our fine-grained personalized learning method leverages frequency domain analysis to extract and retain both fundamental and personalized knowledge from local model parameters. This allows us to build highly accurate personalized models suited to each vehicle's data characteristics. Experimental results show that our method improves model accuracy by up to 10.31% and reduces training time by up to 24.93% compared to the latest personalized federated learning algorithms. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Joint Task Partitioning and Resource Allocation in UAV-Enabled Vehicular Edge Computing Based on Deep Reinforcement Learning

引用

IEEE Internet of Things Journal 2025年

作者： Liang, Hongbin Zhang, Han Ale, Laha Hong, Xintao Wang, Lei Jia, Qiong Zhao, Dongmei Southwest Jiaotong University School of Transportation and Logistics National United Engineering Laboratory of Integrated and Intelligent Transportation National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China Southwest Jiaotong University School of Computing and Artificial Intelligence Chengdu611756 China Southwest Jiaotong University School of Information Science and Technology Chengdu611756 China Chinese Academy of Sciences Laboratory of Noise and Vibration Research Institute of Acoustics Beijing100190 China McMaster University Department of Electrical and Computer Engineering HamiltonONL8S 4K1 Canada

Vehicle Edge Computing (VEC) leverages compact cloud computing at the mobile network edge to meet the processing and latency needs of vehicles. By bringing computation closer to the vehicles, VEC reduces data transmission, minimizes latency, and boosts performance for compute-intensive applications. However, during peak hours of urban road traffic, the scarce computational resources available at edge servers could pose challenges in fulfilling the processing needs of vehicles. Introducing Unmanned Aerial Vehicles (UAVs) as supplementary edge computing nodes could significantly mitigate the aforementioned issue. In this paper, we propose a flexible edge computing framework in which a fleet of UAVs function as mobile computational service providers, offering computation offloading services to multiple vehicles. We design and optimize a computation offloading model for the UAV-enabled vehicle edge computing environment. The proposed model tackles the task offloading challenge, aiming to optimize UAV revenue and task processing efficiency while considering the constraints of UAVs' restricted computational power and energy resources. Towards this end, our model jointly considers two key factors: task partitioning and computational resource allocation. To tackle the challenges posed by the aforementioned non-convex optimization problem, we construct a Markov Decision Process (MDP) model for the multi-UAV-enabled mobile edge computing system and introduce an innovative Multi-Agent Deep Reinforcement Learning (MADRL) framework addressing the decision-making challenge represented by MDP model. Comprehensive simulation outcomes illustrate that our devised task offloading technique outperforms other optimization methods. © 2014 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks

arXiv

引用

arXiv 2025年

作者： Cui, Shuang Li, Yi Li, Jiangmeng Tang, Xiongxin Su, Bing Xu, Fanjiang Xiong, Hui National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China China Department of Computer Science & Engineering the Hong Kong University of Science and Technology Hong Kong

Single image defocus deblurring (SIDD) aims to restore an all-in-focus image from a defocused one. Distribution shifts in defocused images generally lead to performance degradation of existing methods during out-of-distribution inferences. In this work, we gauge the intrinsic reason behind the performance degradation, which is identified as the heterogeneity of lens-specific point spread functions. Empirical evidence supports this finding, motivating us to employ a continual test-time adaptation (CTTA) paradigm for SIDD. However, traditional CTTA methods, which primarily rely on entropy minimization, cannot sufficiently explore task-dependent information for pixel-level regression tasks like SIDD. To address this issue, we propose a novel Siamese networks-based continual test-time adaptation framework, which adapts source models to continuously changing target domains only requiring unlabeled target data in an online manner. To further mitigate semantically erroneous textures introduced by source SIDD models under severe degradation, we revisit the learning paradigm through a structural causal model and propose Causal Siamese networks (CauSiam). Our method leverages large-scale pre-trained vision-language models to derive discriminative universal semantic priors and integrates these priors into Siamese networks, ensuring causal identifiability between blurry inputs and restored images. Extensive experiments demonstrate that CauSiam effectively improves the generalization performance of existing SIDD methods in continuously changing domains. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：